JP5421104B2 - Method and apparatus for switching graphics sources - Google Patents

Description

  The present invention relates to techniques for switching graphics sources in a computer system. More specifically, the present invention relates to a method and apparatus for reducing power by switching graphics sources in a computer system.

  Rapid advances in computing technology have made it possible to perform trillions of computational operations per second on data sets that are sometimes as large as one trillion bytes. These advances are largely dependent on the rapid increase in size and complexity of integrated circuits. Unfortunately, with the increase in size and complexity of integrated circuits, their power consumption has increased as well.

  In parallel development, the rapid spread of broadband wireless networks has created a tremendous demand for portable computer systems. Unfortunately, portable computer systems typically have severe power constraints due to the limited battery power available. These developments have created a strong need for power saving technologies and systems.

  Advances in 3D graphics technology have led many modern computer systems to drive graphics display devices using dedicated graphics processors (sometimes called graphics processing units (GPUs)). . Unfortunately, today's GPUs consume a tremendous amount of power, which significantly reduces the battery life of portable computer systems and also creates heat dissipation problems.

  Often, during a graphics display operation, little graphics processing is required, such as when a user is reading a document on a display device. Unfortunately, prior art graphics processors cannot switch to a sufficiently low power mode to save enough power during these “low activity” periods.

  One solution to conserve power during such “low activity” periods is to move the display device from a high power graphics source (eg, a high performance GPU) to a low power graphics source (eg, a low performance GPU). It is to switch to. Ideally, this switching operation seamlessly alternates between different graphics sources as the system responds to changing graphics processing demands or to changing system needs to limit power consumption. It is necessary to be unaware of the user so that it can be switched.

  Prior art techniques include a mechanical switch that allows a user to switch between a lower performance graphics source and a higher performance graphics source. However, this aggressive technique requires the user to completely reinitialize the computer system each time they switch from one graphics source to another. Requesting the user to reinitialize the computer system to switch from one graphics source to another is unacceptable in many situations. The initialization process is one of the most disruptive operations performed on a computer. Typically, the user must save all his work before reinitializing the computer, which can take a significant amount of time to complete. In addition, the user must first determine whether the graphics processing demand will be higher or lower in the near future, and then wait for the system to re-initialize, and then if the demand changes, one more time. You need to wait for re-initialization.

  Accordingly, there is a need for a method and apparatus that facilitates quick and / or seamless switching between different graphics sources.

  One embodiment of the present invention provides a system for driving a display device by switching from a first graphics processor to a second graphics processor. During operation, the system receives a request from the first graphics processor to switch the signal source driving the display device from the second graphics processor. Upon request, the system first configures the second graphics processor so that the second graphics processor can drive the display device at any time. The system then switches the signal source that drives the display device from the first graphics processor to the second graphics processor, thereby causing the second graphics processor to drive the display device.

  In a variation of this embodiment, the output display signal of the first graphics processor is coupled to the first set of inputs of the selection device, and the output display signal of the second graphics processor is the first of the inputs of the selection device. Combined into two sets. The output of the selection device is coupled to the input of the display device, and the first set of inputs is the selection device before switching the signal source driving the display device from the first graphics processor to the second graphics processor. To the output of. Switching from the first graphics processor to the second graphics processor decouples the first set of inputs from the output of the selection device and couples it to the output of the selection device of the second set of inputs. Including.

  In a further variation of this embodiment, prior to switching the signal source driving the display device from the first graphics processor to the second graphics processor, the system outputs the output display signal of the first graphics processor. And the output display signal of the second graphics processor are sufficiently synchronized, thereby facilitating a seamless switching process without interrupting the graphical output on the display device.

  In a further variation of this embodiment, the system (1) sufficiently synchronizes the timing signal of the first graphics processor and the timing signal of the second graphics processor, and (2) the first The output display signal is sufficiently synchronized by sufficiently synchronizing the data signal of the graphics processor and the data signal of the second graphics processor.

  In a further variation of this embodiment, the system fully synchronizes the output display signal by fully matching the synchronization signals from the two graphics processors.

  In a further variation of this embodiment, the synchronization signal is a display blanking signal.

  In a further variation of this embodiment, the display blanking signal is a vertical blanking signal.

  In a further variant of this embodiment, the switching takes place during the blanking period associated with the display blanking signal.

  In a further variation of this embodiment, the display blanking period is a vertical blanking period.

  In a further variation of this embodiment, the selection device includes a multiplexer or wired OR logic.

  In a variation of this embodiment, the system (1) powers up the second graphics processor as needed, (2) initializes the graphics processor, (3) the second A second graphics processor is constructed by generating an output signal from the graphics processor.

  In a variation of this embodiment, prior to receiving a switch request, the system monitors the level of graphics processing load. The system then generates a switch request based on the level of graphics processing load.

  In a further variation of this embodiment, the first graphics processor is a high power graphics processing unit (GPU) and the second graphics processor is a low power GPU. In this case, the switching request is generated when the level of the graphics processing load is low.

  In a further variation of this embodiment, the first graphics processor is a low power graphics processing unit (GPU) and the second graphics processor is a high power GPU. In this case, the switching request is generated when the level of the graphics processing load is high.

  In a further variation of this embodiment, the low power GPU is integrated with one of the system chips.

  In a variation of this embodiment, the system powers down the first graphics processor after switching.

  In a further variation of this embodiment, the system uses one or more phase locked loops (PLLs) to fully synchronize the output display signal.

  In a variation of this embodiment, switching from the first graphics processor to the second graphics processor includes fading out the display device using the first graphics processor.

  In a variation of this embodiment, the system includes: (1) initializing the display device as needed; (2) redrawing the display device; and (3) fading in the display device. The graphics processor is used to drive the display device.

1 illustrates a computer system according to an embodiment of the present invention. FIG. 2 illustrates a computer system that can switch between different graphics sources to drive the same display device according to embodiments of the invention. 3 is a flow diagram illustrating a process for driving a display device by switching from a first graphics source to a second graphics source according to an embodiment of the present invention. 3 is a flow diagram illustrating a process of switching from a first graphics source to a second graphics source without synchronizing output display signals according to embodiments of the present invention. FIG. 6 illustrates a single vertical blanking period (VBI) and corresponding vertical sync (V-sync) pulse generated by a graphics source according to an embodiment of the present invention. FIG. 4 illustrates two overlapping VBIs generated by two graphics sources according to an embodiment of the present invention. FIG. 2 is a schematic diagram illustrating a technique for synchronizing timing signals between two graphics sources according to an embodiment of the present invention. FIG. 3 is a schematic diagram illustrating another technique for synchronizing timing signals between two graphics sources according to an embodiment of the present invention. FIG. 2 shows a computer system with two graphics sources according to an embodiment of the invention.

  The following description is presented to enable any person skilled in the art to make and use the invention and is provided in the context of a particular application and its requirements. Various modifications to the disclosed embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be used in other embodiments or applications without departing from the spirit and scope of the invention. Can be applied to. Accordingly, the invention is not limited to the illustrated embodiments but is to be accorded the maximum scope consistent with the claims.

  The data structures and codes described in the detailed description are typically stored on a computer readable storage medium, although this may be any code and / or data that can be used by a computer system. Device or medium. This is volatile memory, non-volatile memory, or magnetic and optical storage devices such as disk drives, magnetic tape, CD (compact disc), DVD (digital versatile disc or digital video disc), or currently known Or other media that can store computer-readable media that will be developed later, but is not limited to such.

Computer System FIG. 1 illustrates a computer system 100 according to an embodiment of the invention. As shown in FIG. 1, the computer system 100 includes a processor 102 coupled to a memory subsystem 106, a peripheral bus 108, and a graphics processor 110 via a bridge 104. The bridge 104 can include any type of core logic unit, bridge chip, or chipset that is commonly used to connect components within the computing system 100. In one embodiment of the invention, the bridge 104 is a Northbridge chip. The processor 102 includes, but is not limited to, any type of processor including a microprocessor, a digital signal processor, a device controller, or a computing engine within an instrument.

  It should be understood that one or more components of computer system 100 are located remotely and can be accessed over a network.

  The processor 102 communicates with the memory subsystem 106 via the bridge 104. The memory subsystem 106 includes a plurality of components including one or more memory chips that can be accessed by the processor 102 at high speeds.

  The processor 102 also communicates with the storage device 112 via the bridge 104 and the peripheral bus 108. Storage device 112 includes any type of non-volatile storage device that can be coupled to a computer system. This includes, but is not limited to, magnetic, optical, magneto-optical storage devices, as well as storage devices based on flash memory and / or battery-backed memory.

  The processor 102 further communicates with the graphics processor 110 via the bridge 104. The graphics processor 110 is a dedicated graphics rendering device that provides a signal source to the display device 114 to drive the display device 114. Display device 114 can include any type of display device that can present information to the user in a visual form (including images and text). This includes, but is not limited to, cathode ray tube (CRT) displays, light emitting diode (LED) displays, liquid crystal displays (LCD), organic LED (OLED) displays, surface electric field displays (SED), or electronic paper. Absent.

  The graphics processor 110 performs 2D and 3D graphics rendering operations such as lighting, shading, and transformation with high performance. To achieve high performance, graphics processor 110 may use dedicated video memory 116 to store frame buffers, textures, vertex arrays, and / or display lists.

  The bridge 104 also includes an embedded graphics processor 118. The embedded graphics processor 118 is typically built for moderate performance graphics processing and therefore consumes much less power than the graphics processor 110. Note that in FIG. 1, the embedded graphics processor 118 is not directly coupled to the display device 114 and therefore does not drive it.

  Although the present invention is described using the computer system 100 shown in FIG. 1, the present invention may generally function on any type of computing device that supports multiple graphics processors. Note that you can. Thus, the present invention is not limited to the computer system 100 shown in FIG.

Selective Switching of Graphics Sources FIG. 2 illustrates a computer system 200 that can switch between different graphics sources to drive the same display device according to embodiments of the invention. In FIG. 2, it should be noted that two graphics sources, graphics processor 210 and embedded graphics processor 218, can each independently drive display device 214. However, the graphics source that actively drives the display device 214 at a predetermined time is determined by the selection device 220 that can select two graphics sources. Specifically, the computer system 200 can use the selection device 220 to select a graphics source based on its current operating conditions.

  More specifically, output display signal 222 from graphics processor 210 and output display signal 224 from embedded graphics processor 218 are both coupled to the input of a two-to-one multiplexer (MUX) 220. The output of MUX 220 is controlled by source selection 226, which determines which of the two graphics sources should drive display device 214. In this embodiment, source selection 226 is the output of bridge chip 204, which comprises inherent logic for generating source selection 226. Note that source selection 226 can also be generated by logic blocks other than bridge 204.

  The output display signal from the selected graphics source is then coupled to the input of display device 214, actively driving the display device. Although the selection device is shown as a multiplexer, it can also include any other type of selection device, such as simple wired-OR logic.

  In one embodiment of the present invention, graphics processor 210 and embedded graphics processor 218 can cooperate via path 228 so that their output display signals can be synchronized. Since the output display signal includes a timing signal and a data signal, synchronizing the output display signal includes synchronizing each timing signal and each data signal. Note that path 228 can be implemented using hardware and / or software to facilitate synchronization of the two graphics sources.

  In one embodiment of the present invention, the graphics processor 210 is a high performance graphics processor unit (GPU) that consumes a large amount of power, but the embedded graphics processor 218 uses less power. It is a low-performance GPU that does not consume. In this embodiment, if the graphics processing load is light, the system switches the graphics source from the graphics processor 210 to the embedded graphics processor 218 to drive the display device 214, and then turns the graphics processor 210 on. Save power by completely powering down. On the other hand, if the graphics processing load becomes heavier again, the system switches the graphics source from the embedded graphics processor 218 to the graphics processor 210 again.

  Although graphics processor switching has been described in the context of a stand-alone graphics processor and an integrated graphics processor as shown in FIG. 2, the present invention generally includes two or more graphics processors. Note that each graphics processor, if provided and properly configured, can function for a computer system that can independently drive a display device. In addition, these multiple graphics processors have different operating characteristics, including different power consumption levels. Moreover, each of the plurality of graphics processors may be either a stand-alone graphics processor or a graphics processor integrated in a chip. Accordingly, the present invention is not limited to the computer system 200 shown in FIG.

  It should be noted that the switching technique described above between different graphics sources does not require a computer system shutdown or computer system re-initialization. As a result, the switching process can be far below the time that would be required if re-initialization was required. As a result, the present invention allows for rapid and frequent switching between graphics processors.

  FIG. 3 is a flow diagram illustrating a process for driving a display device by switching from a first graphics source to a second graphics source according to an embodiment of the present invention.

  During operation, the system first requests to switch the signal source of the display device from the first graphics processor actively driving the display device to the second graphics processor in the inactive state. Is received (step 302).

  The switching request may be generated by a user who recognizes the level of graphics processing load. Alternatively, the switch request may be generated internally by the system.

  In one embodiment of the invention, the system software continuously monitors the level of the graphics processing load. More specifically, the system can determine the level of graphics processing load based on the state of the graphics command queue associated with the graphics processor. For example, if the command queue is almost empty, the system asserts a low graphics processing load. On the other hand, if the command queue is almost full, the system asserts a high graphics processing load.

  Then, based on the level of graphics processing load, the system software selects one of the two graphics processors and subsequently issues a switch request when an inactive graphics processor is selected. Generate.

  For example, if the first graphics processor is a high performance GPU that consumes a lot of power, if the system software detects a significant decrease in the graphics processing load, the system software is low performance but consumes Issue a request to switch to a second graphics processor with less power. On the other hand, if the first graphics processor is a low performance, low power GPU, the system will switch to a high performance, high power GPU if the system software detects a significant increase in graphics processing load. Issue the request you want.

  Using system software to monitor the graphics processing load and automatically issue a switch request is much faster and sometimes more energy efficient than a human-initiated request. Please note that. Furthermore, by using the system software, the user can be freed from the work of monitoring the job.

  Next, in response to the switching request, the system configures a second graphics processor in preparation for driving the display device (step 304). In one embodiment of the present invention, configuring the second graphics processor includes: (1) powering on the processor if it is currently powered down; (2) initializing the graphics processor; Or (3) one or more of generating output signals in preparation for powering on the display device.

  The system then switches the signal source driving the display device from the first graphics processor to the second graphics processor, thereby causing the second graphics processor to drive the display device (step 306). ). In one embodiment of the present invention, the switching includes using a selection device such as MUX 220 of FIG. 2, which decouples the first graphics processor and causes the second graphics processor to switch. Connect to the display device. Various timing controls can be used during the switching operation, which will be described in more detail below. In general, more accurate timing control is required to achieve a smoother switching transition, and thus more complicated switching control mechanisms are usually required.

  When the second graphics processor replaces the first graphics processor, the system powers down the first graphics processor to save power. Note that the switching process described above need not reinitialize the entire system to take effect.

  While switching based on graphics processing load has been described, switching requests are also based on power conditions (eg, whether the system is running on battery or external power, or if the battery is low), Note that it can be generated based on the need to reduce the amount of system heat dissipation, based on user preferences, or based on any function or capability that differs between the two graphics processors.

Timing during switching Switching between different graphics processors to drive the same display device requires a certain level of cooperation between the graphics processors to ensure a sufficiently seamless transition. Various timing techniques during switching are described below by distinguishing based on whether synchronization is involved in the output display signal.

Switching Without Synchronization FIG. 4 is a flow diagram illustrating a process for switching from a first graphics source to a second graphics source without synchronizing the output display signal according to an embodiment of the present invention.

  During operation, the first graphics processor fades out the display device (step 402). This can be done in several ways, including displaying black or other colors on the screen, turning off the backlight, or powering down the entire display device. Note that this is not the case.

  The system then switches the signal source driving the display device from the first graphics processor to the second graphics processor, wherein the second graphics processor is configured to drive the display device. (Step 404). More specifically, the switching includes decoupling the output signal of the first graphics processor from the input of the display device and coupling the output signal of the second graphics processor to the input of the display device.

  When the switching is completed, the second graphics processor initializes the display device as necessary (step 406). Next, the second graphics processor redraws the display screen, and then fades in the display screen (step 408).

  In this embodiment, the two graphics sources need not be synchronized with each other. As a result, the second signal source need not be configured to redraw the display device before switching takes place. Further, the first signal source can be turned off prior to switching (eg, via a fade-out operation).

  Note that switching without synchronization is straightforward, but makes the user aware of the switch. However, if the switching can be completed in an instant, the user need not be aware of the switching. Alternatively, if switching takes place over time, reducing visual interruptions by using appropriate visual effects such as the fade-out / fade-in effects used when the display resolution is changed Can do. In general, the undesirable visual effect of switching from one set of display signals to another set of unsynchronized display signals can be made inconspicuous by fading out the display device during transition.

Switching with synchronization Synchronizing the output signal prior to switching facilitates a smoother, less noticeable or seamless switching process without interrupting the graphical output on the display device. However, prior to switching, the second graphics processor may begin generating output signals in preparation for driving the display so that the output display signals from both graphics sources are synchronized. Necessary.

  In one embodiment of the invention, synchronization of output signals from two graphics sources can be achieved by matching timing information embedded in the output signals. Such timing information includes, but is not limited to, horizontal synchronization (H-sync) pulses, vertical synchronization (V-sync) pulses, horizontal blanking signals, and vertical blanking signals. In particular, the V-sync pulse controls the image refresh of the display device by indicating when to start scanning a new frame of data. V-sync pulses typically occur within a short interval between two consecutive image frames called the vertical blanking period (VBI), during which the on-screen display remains constant for various housekeeping purposes. Is maintained in the state. FIG. 5A shows a single VBI 502 and corresponding V-sync pulse 504 generated by a graphics source according to an embodiment of the present invention. Note that V-sync pulse 504 is within VBI 502.

  In this embodiment, the computer system keeps track of when a V-sync pulse has occurred at the first graphics source and the second graphics source's timing sequence is tracked by the V-sync pulse at the first. Adjust until it matches one graphics source. In one embodiment, combining the V-sync pulses from the two graphics sources uses either software or hardware to convert the timing sequence of the second graphics source to the first Includes matching with graphics source. During this alignment, the first graphics source continues to drive the display device. When the V-sync pulse is well aligned between the two sources, a switch is performed during the next VBI.

  FIG. 5B shows two overlapping VBIs, VBI 506 and VBI 508, generated by two graphics sources according to an embodiment of the present invention. Note that the switching occurs within the overlapping period 510 of the two VBIs. It should also be noted that the switching process occurs without the user's knowledge if it can be completed within the overlap period 510. In addition, by sufficiently synchronizing the two graphics sources, the second graphics source will immediately start driving the display device so that it appears to the user that the display has not changed.

  However, it may take longer than a single VBI to complete the switching process, or it may take several frame times to resolve. In this case, the system can make the effect of switching inconspicuous by completely blanking or fading out the screen.

  In another embodiment of the invention, rather than aligning the second graphics source with the first graphics source, the system causes the V-sync signal of the second graphics source to be the first. Can be drifted against any graphics source. Such drift of the timing signal may result from one or more timing differences. For example, drift is caused by slight differences in the clock frequencies of two graphics processors. Alternatively, drift can be caused by programming the two graphics processors to operate at slightly different display frame rates.

  In this embodiment of synchronization, the system monitors two V-sync signals to detect when two V-sync signals from two sources overlap each other. Monitoring can be performed in either software or hardware. If this occurs, the system can switch from one graphics source to the other before the two signals drift away from each other.

Switching with Hardware-Based Synchronization In one embodiment of the present invention, additional hardware is used to accurately match the display output timing of the two graphics sources. Synchronize one with the other graphics source. The switch is then performed during the next VBI so that the switch is not detected by the user. In this embodiment, additional hardware is used to adjust the phase and frequency of the display timing generator of the second graphics source so that its display output timing matches the display output timing of the first graphics source. By incorporating the wear, smoother switching is possible.

  FIG. 6A is a schematic diagram illustrating a technique for synchronizing timing signals between two graphics sources according to an embodiment of the present invention. As shown in FIG. 6A, the two graphics sources A and B comprise a timing generator 602 and a timing generator 604, respectively. Timing generator 602 generates a V-sync pulse at graphics source A output V-SYNC 606 and a vertical blanking period at output VBI 608, while timing generator 604 generates a graphics source A. A V-sync pulse is generated at the B output V-SYNC 610 and a vertical blanking period is generated at the output VBI 612.

Graphics sources A and B also provide a frequency reference for timing generators 602, 604 using phase locked loop (PLL) 614 and PLL 616, respectively. More specifically, PLL 614 and PLL 616 receive reference frequency inputs f ^A _REF 618 and f ^B _REF 620 from the left, and as inputs to timing generators 602 and 604, reference frequency outputs f ^A _OUT 622 and f ^B _OUT 624 is generated. Detailed descriptions of the functionality of PLLs and related components can be found in several references describing PLLs (Floyd M. Gardner, “Charge-Pump Phase-Lock Loops” IEEE Transactions on Communications, Vol. 28, No. 11, see November 1980).

For frequency synchronization, the PLL 614 includes a divider M _A 626 and a divider N _A 628. Similarly, the PLL 616 includes a divider M _B 630 and a divider N _B 632. The outputs of PLL 614 and PLL 616 are output frequencies f ^A _OUT = f ^A _REF × (M _A / N _A ) and f ^B _OUT = f ^B _REF × (M _B / N _B ), respectively, in the case of phase synchronization. Is generated.

In one embodiment of the invention, the frequency scalar values M _A , M _B , N _A , N _B are programmable and stored in a programmable register. Specifically, the scalars M _A , M _B , N _A , N _B are coupled to the controller 634 and can be programmed via the controller 634, which can be done in software or in a microcontroller or finite state machine. Can be implemented in hardware. The controller 634 receives the input switching request REQSW 636, and in addition, the clock signals V-SYNC _A 606 and VBI _A 608 from the graphics source _A , and the clock signals V-SYNC _B 610 and VBI _B from the graphics source _B. 612 is received. Controller 634 then measures the phase difference between the V-sync or VBI signals of the two graphics sources. The controller 634 then uses the measured phase difference as a feedback signal to synchronously change the M and N values of the associated PLL so that V-sync and VBI from one graphics source. The phase can be adjusted relative to the other graphics source.

  The controller 634 uses the feedback loop and continues to measure and adjust the phase difference. If the controller 634 determines that the phase difference is within a predetermined boundary, it generates a switchable OK2SWITCH 638. In one embodiment of the invention, OK2SWITCH 638 is coupled to source selection 204 of FIG. 2, which causes MUX 220 to switch sources.

  It should be noted that the above description allows the clocks of both active and inactive graphics sources to be changed. In particular, if the PLL scalar value to be changed is associated with a source that actively drives the display device, it may be desirable to smoothly adjust the associated frequency over time. It should also be noted that it is not necessary to be able to switch completely in time with the clock. In one embodiment, the controller 634 can be configured to match VBIs without overlap, so that switching operations do not cause significant artifacts. If the controller detects that there is sufficient overlap, it will assert the OK2SWITCH signal to complete the synchronization.

  FIG. 6B is a schematic diagram illustrating another technique for synchronizing timing signals between two graphics sources according to an embodiment of the present invention.

  In this embodiment, a single PLL 640 is used to synchronize the timing signals between graphics sources A and B. Note that there is no direct control of the PLL by the controller as in FIG. 6A. Instead, PLL 640 forms a closed loop with one of the timing generators.

As shown in FIG. 6B, timing generators 602 and 604 receive reference frequency inputs f _{REF_A} 642 and f _{REF_B} 644, respectively. The four outputs from timing generators 602, 604, V-SYNC _A 606, VBI _A 608, V-SYNC _B 610, and VBI _B 612 are coupled to a 4 to 2 multiplexer MUX 646, which is Either V-SYNC _A 606 and V-SYNC _B 610 or VBI _A 608 and VBI _B 612 are selected as outputs. The output of MUX 646 is then coupled to the input of PLL 640 phase detector. Note that in this embodiment, it can be used to match either the V-sync signal or the VBI signal.

  The VCO output from PLL 640 is then coupled to one of the timing generators and serves as the input reference frequency, thereby completing the closed loop at that timing generator. More specifically, the output from PLL 640 is initially coupled to the inputs of two multiplexers MUX 648 and MUX 650, which further receive external clock signals EXTCLK_A 652 and EXTCLK_B 654, respectively, as inputs. The outputs of MUX 648 and MUX 650 are controlled by controller 656, which selects either the external clock source or the PLL output as the reference frequency input for each timing generator. Note that the controller 656 receives input from the phase detector of the PLL 640 and detects whether the PLL 640 is locked based on the input.

Assume that during operation, graphics source A is actively driving the display. Meanwhile, the VCO output of PLL 640 is selected as the reference frequency f _{REF_B} 644 of graphics source B timing generator 604. Thus, PLL 640 and timing generator 604 form a closed loop that facilitates the selected timing signal (either V-sync or VBI) from the two timing generators to be sync-up. To do. When controller 656 detects that PLL 640 is in phase synchronization, it switches the graphics source driving the display device from graphics source A to graphics source B during the next blanking period. . More specifically, in subsequent blanking intervals, the controller 656 _switches the f _{REF_B} input from the PLL 640 to the external clock source EXTCLK_B 654. After switching, PLL 640 can be used to lock graphics source A to graphics source B, but since then graphics source B is actively driving the display.

Selecting a graphics processor without switching In one embodiment of the present invention, instead of switching between two graphics processors to drive the same display device, a low performance, low power graphics processor is always present. The display device is driven. In this embodiment, if additional graphics performance is required, the high performance processor takes over the graphics processing load and renders its display image in the same frame buffer used by the low performance processor. When the system is operating in this way, a low performance processor functions purely as a display output device, that is, transfers image data from the frame buffer to the display device, while a high performance device does not support all graphics. Execute the process. If high performance is not required, the low performance device can take over the graphics processing task again and the high performance device can be powered off accordingly.

  FIG. 7 illustrates a computer system 700 comprising two graphics sources according to an embodiment of the present invention. A low performance, low power graphics processor 712 is coupled directly to the display 714 and always drives the display. On the other hand, a high performance, high power graphics processor 716 is coupled to the graphics processor 712 and is normally powered off when not in use.

  If additional graphics processing power is required, the system powers up the graphics processor 716 to provide additional graphics rendering capacity. However, instead of rendering graphics into its own frame buffer, graphics processor 716 renders the image directly into the graphics processor 712 frame buffer, which is displayed by continuous refresh. Responsible for displaying graphics on device 714.

  Since the display device is always driven by the same graphics processor, this approach does not require hardware switching and does not have the effect of hardware switching transitions that should not be recognized by the user. Please note that.

  The foregoing descriptions of embodiments of the present invention have been presented for purposes of illustration and description only. The description is not intended to be exhaustive or to limit the invention to the form disclosed. Accordingly, many modifications and variations will be apparent to practitioners skilled in this art. In addition, the above disclosure is not intended to limit the present invention. The scope of the present invention is defined by the appended claims.

Claims (14)

A computer-readable storage medium that stores instructions that, when executed by a computer, cause the computer to execute a method of switching from a first graphics processor to a second graphics processor to drive a display device. The method is
Generating a signal source for driving the display device for the first plurality of image frames using the first graphics processor, the second graphics processor including the first graphics processor; A step inactive for a plurality of image frames of
Receiving a request from the first graphics processor to switch the signal source driving the display device to the second graphics processor;
In response to the request,
Configuring the second graphics processor so that the second graphics processor can drive the display device at any time;
Switching the signal source driving the display device from the first graphics processor to the second graphics processor, thereby causing the second graphics processor to drive the display device;
Before switching from the first graphics processor to the second graphics processor, the output display signal of the first graphics processor and the output display signal of the second graphics processor are synchronized. Performing a seamless switching process without interrupting the graphical output on the display device;
Generating a signal source for driving the display device for the second plurality of image frames using the second graphics processor, the first graphics processor including the second graphics processor; A step inactive for a plurality of image frames of
A computer-readable storage medium comprising: A computer system that switches from a first graphics processor to a second graphics processor to drive a display device,
A processor;
Memory,
A first graphics processor;
A second graphics processor, wherein the first graphics processor and the second graphics processor have different operating characteristics;
A switching mechanism coupled to the first graphics processor and the second graphics processor;
A display device coupled to the switching mechanism, wherein the switching mechanism is configured to couple one of the two graphics processors to the display device at a predetermined time, the second graphics A display device that is initially coupled to the first graphics processor for at least a first plurality of image frames while the graphics processor is in an inactive state;
A receiving mechanism configured to receive a request from the first graphics processor to switch the signal source driving the display device to the second graphics processor;
A machine configuration for executing the step of configuring the second graphics processor to the second graphics processor to drive the display device at any time,
Before switching from the first graphics processor to the second graphics processor, the output display signal of the first graphics processor and the output display signal of the second graphics processor are synchronized. and synchronize mechanism executing step, thereby facilitating seamless switching process without interrupting the graphical output in the display apparatus,
With
The switching mechanism, the first of the signal source from the graphics processor to drive the display device to the second graphics processor to perform the toggle its steps, whereby the first graphics processor computer system but while in the inactive state, in which for at least a second plurality of image frames, characterized that you driving the display device to the second graphics processor. The output display signal of the first graphics processor is coupled to a first set of inputs of a selection device;
An output display signal of the second graphics processor is coupled to a second set of inputs of the selection device;
An output of the selection device is coupled to an input of the display device;
Prior to switching the signal source driving the display device from the first graphics processor to the second graphics processor, the first set of inputs is coupled to the output of the selection device;
Switching the signal source driving the display device from the first graphics processor to the second graphics processor comprises:
Decoupling the first set of inputs from the output of the selection device;
Coupling the second set of inputs to the output of the selection device;
The computer system according to claim 2, comprising:   The computer system of claim 2, wherein the synchronization mechanism is configured to synchronize the output display signal using one or more phase locked loops (PLLs).   3. The computer system of claim 2, wherein synchronizing the output display signal includes aligning the synchronization signals of the two graphics processors. 3. The computer system according to claim 2 , wherein the synchronization signal is a vertical blanking signal. The selection device is:
Multiplexer or
The computer system of claim 2, comprising wired OR logic. The step of configuring the second graphics processor includes:
Powering up the second graphics processor as needed;
Initializing the second graphics processor;
Generating an output signal from the second graphics processor;
The computer system according to claim 2, comprising: A monitoring mechanism configured to monitor the level of the graphics processing load;
A generation mechanism configured to generate the switching request based on the level of graphics processing load;
The computer system according to claim 2, further comprising: If the first graphics processor is a high power graphics processing unit (GPU), the second graphics processor is a low power GPU; or
The computer system of claim 2, wherein when the first graphics processor is a low power GPU, the second graphics processor is a high power GPU. The computer system of claim 10 , wherein the low power GPU is integrated with one of the system chips.   Switching from the first graphics processor to the second graphics processor includes fading out the screen of the display device using the first graphics processor. The computer system according to claim 2. Driving of the display apparatus according to the second graphics processor,
It said display device initializes as necessary,
Redraw screen of the display device,
Fading in the screen of the display device ;
The computer system according to claim 2 , comprising: The first graphics processor is a high power graphics processing unit (GPU), and the second graphics processor is a low power GPU;
The computer system of claim 10, wherein a switch request is generated when the level of graphics processing load is low.

Images